Searcharxiv⌕ Search

arXiv subjects

Jiaying Wu

Publications and source records attributed to Jiaying Wu.

At least 19 recordsLinked to original sources
arXiv2026

When Platforms Pay Users to Correct Misinformation: Revenue Incentives and Governance Capacity in Weibo Annotations

Crowdsourced misinformation governance systems such as Community Notes and Weibo Annotations depend on sustained corrective labor. How monetary incentives shape participation and subsequent governance outcomes remains poorly understood. We conduct a mixed-methods study of Weibo Annotations, analyzing 102,994 posts and 431,407 comments from 2023--2026, alongside interviews with 15 contributors. We find concentrated corrective labor, limited observed display, and weak quality--engagement alignment. Policy introduction was associated with sharp increases in contributor participation and annotation production. Model-assisted quality followed its expected trajectory, evidence for additional display growth was inconclusive, and engagement per annotation fell below expectation. Public discussions and interviews reveal substantial verification demands, difficult-to-interpret review processes, uneven platform knowledge, and gaps in contributor protection. We identify four recurring bottlenecks in governance orchestration: participation, review, reach, and protection. Effective incentive design therefore depends on whether platforms can support these downstream processes as corrective labor expands.

cs.SI↗
arXiv2026

No Note Is an Island: Probing LLMs' Understanding of Crowdsourced Fact-Checking Environments

Large language models (LLMs) increasingly assist crowdsourced fact-checking, yet evaluations focus on individual annotations. A correction's reach and reception depend on visibility, audience responses, and platform policies. We introduce correction context understanding: assessing corrective content, interpreting audience responses, and reasoning about platform dynamics within a shared environment. We build NoteHabitat from 36 months of Weibo Annotations data, linking 102,994 posts (42,853 annotations), 431,407 comments, and five policy events. Evaluating diverse model families across seven tasks spanning content, interaction, and management reveals three gaps. Annotation quality correlates only weakly with engagement ($ρ=0.068$), while four zero-shot LLMs systematically underrate quality relative to human judgments, especially evidence support and objectivity. Models also miss toxic comments supporting corrections (36.4% average recall across ten models). At the platform level, LLMs partially predict policy-associated outcome directions, but LLM-guided simulations poorly reproduce daily activity. Cross-group analyses expose blind spots tied to contribution types and reader stances that aggregate scores conceal. Reliable fact-checking AI must understand the note, the conversation around it, and the platform in which both unfold.

cs.SI↗
arXiv2026

SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents

We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents. It contains 7.4K human-in-the-loop synthesized samples spanning three layers of agent action space: (i) Code Generation, (ii) File Management, and (iii) System Interaction. Across these categories, SWE-MISBEHAVIOR covers 11 distinct misbehaviors with a fully automated evaluation protocol, including coding-action violations, Create/Read/Update/Delete (CRUD) file misbehaviors, system integrity and abuse violations, and task-goal misalignment. Experiments on state-of-the-art open-source coding agents (e.g., OpenHands, smolagents) reveal substantial misaligned behaviors, including dependency misinterpretation (up to 98.5% of cases), unintended modification of user inputs (50.5%), and silent compromise of environment integrity (53%). Motivated by these findings, we further propose CODE-KIT, a lightweight adaptive framework that combines misbehavior-aware guidelines with novel tools to help agents avoid such failures. CODE-KIT reduces misbehaviors by 52% for smolagents and 34% for OpenHands, while simultaneously improving task completion performance.

cs.SE↗
arXiv2026

Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models

Multimodal adaptation can weaken temporal reasoning (TR) in video-language models (VLMs) even when the visual evidence needed for an answer is correctly perceived. This weakened competence, however, remains partly recoverable from the model's paired pre-adaptation language checkpoint. We introduce MERIT, a gradient-free framework that selectively restores this competence across the language backbone while protecting temporal perception (TP). It assigns each self-attention layer a VLM-dominant or LLM-dominant interpolation and uses the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to search the recipe space under a perception-constrained objective. Across three VLM families and five video benchmarks, MERIT improves reasoning-aligned performance in all 15 model--benchmark evaluations while preserving TP across all three Video-MME settings. Recipes selected using 232 diagnostic examples transfer to four unseen benchmarks, with relative gains up to 27.8%, and outperform full-backbone, uniform-attention, and alpha-tuned random-layer merging. Interventional masking shows that MERIT-selected layers are disproportionately important for TR, while frame-level attribution reveals increased reliance on temporally distributed, causally relevant evidence. These results show that adaptation-induced reasoning degradation can be repaired post hoc through selective reuse of pre-adaptation competence, without learning new parameters or adding inference overhead.

cs.CV↗
arXiv2026

Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes

Large Language Model (LLM)-augmented Community Notes offer a scalable path for timely, evidence-grounded correction of health misinformation on social platforms. However, they still reset at every post, leaving useful correction experience from prior cases unused. We introduce EvoNote, an agentic framework that enables health Community Notes generation to self-evolve through an evolving experience memory of prior misinformation correction episodes. Its core is fine-grained credit assignment: EvoNote grounds trajectory-level feedback in health-specific note qualities and distills it into action-level memory for claim analysis, evidence acquisition, and note writing. We evaluate EvoNote on MM-HealthCN, a 1.2K-instance multimodal benchmark of user-flagged health posts with human-written Community Notes and crowd-derived helpfulness labels. Under a human-validated hierarchical utility judge, EvoNote-generated notes are preferred over corresponding human-written notes in 89.6% of cases; on a separate set of Needs More Ratings posts without a crowd helpfulness verdict, EvoNote produces helpful notes for 82.0% of cases. It also reduces time to an available candidate correction from multi-hour post-to-note delays to under 2 minutes on average. Analyses link these quality gains to stronger evidence use and reusable correction strategies, positioning self-evolving note generation as a promising paradigm for scalable health misinformation governance.

cs.CL↗
arXiv2026

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for understanding how effectively agents acquire and use new knowledge. Existing benchmarks have sought to evaluate this ability, but they primarily evaluate tasks whose rules are provided in the instructions or already familiar to pretrained models, making it difficult to distinguish learning from interactions from reasoning with existing knowledge. To address this, we introduce Learn2Play Bench, a benchmark of newly designed text-based games, whose rules are novel or counterintuitive, requiring agents to acquire knowledge through interaction rather than rely solely on pretrained knowledge. These games provide reproducible feedback and automatic scoring, enabling controlled evaluation of learning across repeated attempts. We also vary game instances to test whether agents can apply what they have learned to new situations. Therefore, we evaluate how backbone models, self-evolving methods, and agent harnesses affect agents' learning ability, revealing three findings: (1) Experience retention: Retaining complete records of actions and feedback can support more effective learning than summarizing these experiences into rules or strategies. (2) Human agent gap: Top-performing human players achieve higher peak scores than the evaluated agents. Human explore more varied strategies, and repeat actions less. (3) Harness matters: With the backbone fixed, changing the harness can improve performance while reducing estimated inference cost. Together, these findings provide insights into how LLM agents learn from experience and suggest directions for future work to improve their learning ability. Project website: https://liushiliushi.github.io/learn2play-bench-website/

cs.AI↗
arXiv2026

Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration

Multi-agent systems are often judged by whether they reach the correct answer. This can miss a distinct failure: collaboration may leave behind a corrupted information state even when the immediate decision is correct. We call this an off-query failure. To study this failure in collaborative decision support, we introduce OffQuery, which separately evaluates evidence verification (T1), shared-state reconstruction (T2), and task resolution (T3) in two representative high-stakes settings: healthcare and disaster response. Across GPT, Gemini, and Qwen models, standard collaboration shows much stronger task performance than state reliability. Averaged over 21 model--setting combinations, task resolution reaches 64.7%, while evidence verification and state reconstruction reach only 14.3% and 43.1%. We trace this gap to selective information use: current queries often bypass corrupted facts, which become consequential when later tasks require them. We further introduce ReGround, which resolves conflicting evidence, verifies shared facts, reconstructs a trusted state, and reasons over that state. Across seven models from three families, ReGround improves all three capabilities in every evaluated setting, with average relative gains of 309.0%, 82.9%, and 17.6% on T1, T2, and T3. Reliable collaboration therefore requires both a correct decision and a reliable shared state for future reasoning.

cs.CL↗
arXiv2026

When Does AI Augment Work? A Workflow-Level Framework for Human-Agent Collaboration

We aim to characterise the value of artificial intelligence in the workplace. Current studies largely measure this value in terms of the current automation capabilities and public adoption of AI. However, such metrics ignore the greater impacts of human--agent collaboration in transforming the nature of work. To account for this, we must expand the scope of our analysis beyond atomised tasks of today, and instead focus on how AI can augment entire workflows of the future. To ground this analysis, we establish a precise definition of AI augmentation comprising six conditions, spanning durable net value, meaningful human control, accountability and recovery, and long-term human development through learning, career pathways, and job purpose. We elaborate on these conditions and apply the framework in a case study of AI-mediated social surveys. We conclude by outlining how organisations, researchers, and government leaders can use this framework to make sense of the future of work.

cs.AI↗
arXiv2026

Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models

Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources. To evaluate this missing capability, we introduce ST-OmniQA, a spatio-temporal audio-visual question-answering benchmark built from panoramic videos paired with synchronized first-order Ambisonics (FOA) audio of moving sound sources. It contains 40K videos and 400K question-answer pairs organized into four capability levels covering sound-event recognition, direction of arrival, source distance, motion trajectories, and temporally grounded audio-visual reasoning. Building on this benchmark, we propose ST-Omni-R1, which integrates FOA-derived semantic and trajectory representations with panoramic visual context and is trained through progressive curriculum learning and reasoning-tree reinforcement learning. ST-Omni-R1 achieves 77.83\% average semantic accuracy across the four levels, compared with 37.28\% for the best evaluated baseline. Results on three public spatial-audio benchmarks further indicate that its learned spatial and motion representations transfer beyond ST-OmniQA.

cs.AI↗
arXiv2026

LLM-based Human Simulations Have Not Yet Been Reliable

Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant discrepancies between their outcomes and authentic human actions. Our investigation begins with a systematic review of LLM-based human simulations in social, economic, policy, and psychological contexts, identifying their common frameworks, recent advances, and persistent limitations. This review reveals that such discrepancies primarily stem from inherent limitations of LLMs and flaws in simulation design, both of which are examined in detail. Building on these insights, we propose a systematic solution framework that emphasizes enriching data foundations, advancing LLM capabilities, and ensuring robust simulation design to enhance reliability. Finally, we introduce a structured algorithm that operationalizes the proposed framework, aiming to guide credible and human-aligned LLM-based simulations. To facilitate further research, we provide a curated list of related literature and resources at https://github.com/Persdre/awesome-llm-human-simulation.

cs.CL↗
arXiv2026

Simulation of Non-Markovian Quantum Accelerated Dynamics via Time-Fractional Schrödinger Equation

The Time-Fractional Schrödinger Equation (TFSE) is an effective tool for simulating the dynamics of non-Markovian quantum systems. The Quantum Speed Limit (QSL) time characterizes the minimum time required for the evolution of a non-Markovian quantum system. In this paper, Wei's TFSE is employed to simulate the non-Markovian quantum accelerated evolution process in the Resonant Dissipative Jaynes-Cummings (RDJC) model. By solving the QSL time of a time-fractional single-qubit open system, the enhancement mechanism of the system evolution speed induced by the non-Markovian memory effects of the environment is revealed. Further studies show that the optimized acceleration of the system evolution can be achieved by jointly regulating the fractional order, coupling strength, and photon number. Comparative analyses indicate that Wei's TFSE can accurately capture the non-Markovian accelerated dynamical features of the system over the entire fractional order range, whereas Naber's TFSE is applicable only within a limited fractional order interval. In addition, the comparisons of the average simulation time for calculating the dynamical trajectory of the excited-state probability demonstrate that Wei's TFSE has a significant simulation advantage in computational efficiency. Therefore, Wei's TFSE is more accurate and efficient for simulating the accelerated dynamics of non-Markovian quantum systems.

quant-ph↗
arXiv2026

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.

cs.CL↗
arXiv2026

The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation

Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts and viewpoints needed to interpret an issue. We identify the deliberative illusion: discussion produces (1) factual attrition, the progressive loss of issue-critical facts, alongside (2) stance homogenization, the collapse of diverse positions toward consensus. To measure this process, we introduce DelibTrace, a framework that decomposes each issue into atomic facts, labels issue-critical ones, distributes them across agents, and tracks their survival across discussion rounds. Across ethical and news-based deliberation with three representative LLM families, multi-agent discussion erases up to 72% of issue-critical facts. This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context. These results reveal a sharper risk: agents can agree more while knowing less. We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.

cs.CL↗
arXiv2026

Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation

Community Notes, the crowd-sourced misinformation governance system on X (formerly Twitter), allows users to flag misleading posts, attach contextual notes, and rate the notes' helpfulness. However, our empirical analysis of 30.8K health-related notes reveals substantial latency, with a median delay of 17.6 hours before notes receive a helpfulness status. To improve responsiveness during real-world misinformation surges, we propose CrowdNotes+, a unified LLM-based framework that augments Community Notes for faster and more reliable health misinformation governance. CrowdNotes+ integrates two modes: (1) evidence-grounded note augmentation and (2) utility-guided note automation, supported by a hierarchical three-stage evaluation of relevance, correctness, and helpfulness. We instantiate the framework with HealthNotes, a benchmark of 1.2K health notes annotated for helpfulness, and a fine-tuned helpfulness judge. Our analysis first uncovers a key loophole in current crowd-sourced governance: voters frequently conflate stylistic fluency with factual accuracy. Addressing this via our hierarchical evaluation, experiments across 15 representative LLMs demonstrate that CrowdNotes+ significantly outperforms human contributors in note correctness, helpfulness, and evidence utility.

cs.SI↗
arXiv2026

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems

Multi-agent systems (MAS) powered by large language models (LLMs) increasingly adopt planner--executor architectures, where planners convert prompts into subtasks, roles, dependencies, and routing paths. This flexibility enables adaptive coordination, but exposes an attack surface in workflow formation: prompts can shape agent organization without modifying MAS infrastructure. We study this risk through social influence probing workflows to identify high-impact subtasks and malicious-signal propagation. The analysis reveals two vulnerabilities: workflow position can amplify or suppress a malicious signal, and sycophantic framing makes downstream agents more likely to relay it. We translate these findings into FlowSteer, a prompt-only workflow steering attack that converts vulnerability priors into one crafted prompt. FlowSteer aligns a malicious signal with influential task components and guides replanning toward dependencies that preserve propagation. Experiments show that FlowSteer increases malicious success by up to 55% over naive prompting, transfers across MAS setups, and remains effective with black-box topology inference. As FlowSteer biases the planning signals that generate the workflow, MAS defenses that inspect only the generated workflow provide limited protection. As such, we introduce FlowGuard, an input-side defense that reduces malicious success by up to 34% while preserving prompt utility. Our results position workflow formation as a new safety frontier for multi-agent LLM systems, opening a planning-time security perspective on how agent coordination itself can be attacked and defended.

cs.CR↗
arXiv2026

XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration

Despite the growing adoption of large language models (LLMs) in academic workflows, their capabilities remain limited in supporting high-quality scientific writing. Most existing systems are designed for general-purpose scientific text generation and fail to meet the sophisticated demands of research communication beyond surface-level polishing, for example, maintaining conceptual coherence across sections. Furthermore, academic writing is inherently iterative and revision-driven, a process that is not well supported by direct prompting-based paradigms. To address these scenarios, we propose a human-AI collaboration framework for academic paper revision, centered on criteria-guided intent alignment and context-aware modeling. To validate the framework, we curate a dataset of 7,000 research papers from top-tier venues, annotated with 140,000 instruction--response pairs that reflect realistic, section-level scientific revisions. We instantiate the framework in XtraGPT, the first suite of open-source LLMs (1.5B to 14B parameters) specifically fine-tuned for context-aware academic paper revision. Extensive experiments show that XtraGPT significantly outperforms same-scale baselines and rivals the quality of proprietary counterparts. Both automated preference assessments and human evaluations confirm the effectiveness of XtraGPT in improving scientific drafts. Our code and models are available at https://github.com/Xtra-Computing/XtraGPT and https://huggingface.co/collections/Xtra-Computing/xtragpt.

cs.CL↗
arXiv2026

What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews

Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports. This covert harm is subtler than explicit misinformation, yet remains underexplored. To address this gap, we develop a multi-stage pipeline that simulates preview-based and context-based understanding, enabling construction of the MM-Misleading benchmark. Using MM-Misleading, we systematically evaluate open-source LVLMs and uncover pronounced blind spots in omission-based misleadingness detection. We further propose OMGuard, which combines (1) Interpretation-Aware Fine-Tuning for misleadingness detection and (2) Rationale-Guided Misleading Content Correction, where explicit rationales guide headline rewriting to reduce misleading impressions. Experiments show that OMGuard lifts an 8B model's detection accuracy to the level of a 235B LVLM while delivering markedly stronger end-to-end correction. Further analysis shows that misleadingness usually arises from local narrative shifts, such as missing background, instead of global frame changes, and identifies image-driven cases where text-only correction fails, underscoring the need for visual interventions.

cs.CV↗
arXiv2026

Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models

The impact of multimodal misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators deliberately embed. Interpreting such creator intent is therefore essential for multimodal misinformation detection (MMD) and effective information governance. To this end, we introduce DeceptionDecoded, a large-scale benchmark of 12,000 image-caption pairs grounded in trustworthy reference articles, created using an intent-guided simulation framework that models both the desired influence and the execution plan of news creators. The dataset captures both misleading and non-misleading cases, spanning manipulations across visual and textual modalities, and supports three intent-centric tasks: (1) misleading intent detection, (2) misleading source attribution, and (3) creator desire inference. We evaluate 14 state-of-the-art vision-language models (VLMs) and find that they struggle with intent reasoning, often relying on shallow cues such as surface-level alignment, stylistic polish, or heuristic authenticity signals. To bridge this, our framework systematically synthesizes data that enables models to learn implication-level intent reasoning. Models trained on DeceptionDecoded demonstrate strong transferability to real-world MMD, validating our framework as both a benchmark to diagnose VLM fragility and a data synthesis engine that provides high-quality, intent-focused resources for enhancing robustness in real-world multimodal misinformation governance.

cs.CV↗